Hugo Penedones

Freelancer | Machine Learning research engineer

Machine Learning Research Engineer with 10+ years of experience, with particular interest in Reinforcement Learning. Enjoys finding neat solutions for real world problems.

Hugo is a Machine Learning research engineer who has worked in computer vision, search, bioinformatics and reinforcement learning, at places like the European Space Agency, EPFL, Microsoft and Google DeepMind. After 13+ years abroad, Hugo is back to Portugal to start something new and be part of the vibrant ML community here."


Reinforcement Learning and Long-Term Value Prediction
In recent years, the conjunction of Deep Learning and Reinforcement Learning (RL) has achieved great successes in the areas of robotics and computer games (Atari, Go, Starcraft, DOTA). In this talk we will introduce some of the fundamental concepts of RL, and give you pointers for you to play with those even inside your browser. We will then explain how the same framework allows you to think of other sequential decision making processes, and how you can predict the long-term value of your actions. This translates directly into potential real-world applications ranging from recommender systems to complex industrial controls.